Safety Verification of Deep Neural Networks
- Submitting institution
-
The University of Liverpool
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 12106
- Type
- E - Conference contribution
- DOI
-
10.1007/978-3-319-63387-9_1
- Title of conference / published proceedings
- Computer Aided Verification
- First page
- 3
- Volume
- 10426
- Issue
- -
- ISSN
- 1611-3349
- Open access status
- Deposit exception
- Month of publication
- -
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 104
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper initiated the study of the safety verification problem for modern deep neural networks (see, for example, the blog post by Ian Goodfellow at https://bit.ly/2Fs0f47). The authors have been invited to present their approach in multiple keynote talks, for example at ASE 2020, ESEC/FSE 2019, CONCUR 2019, and ICST 2018. The significance and originality of this contribution have been recognised through the funding of follow-up research projects, including ERC Advanced Grant FUN2MODEL (Kwiatkowska) and EU H2020 project FOCETA (Huang as Liverpool lead).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -